Classification of Nuts Using Deep Learning

Abstract: Nut, hard-shelled seeds enclosing a single edible oily kernel, are generally used for human consumption. Nuts may be consumed as shelled whole nuts or, after blanching, roasted. There are many types of nuts such as: almonds, walnuts, pecans, hazelnuts, cashews, pistachios, macadamia nuts, and brazil nuts. Nut classification has numerous applications across industries, agriculture, and services. For instance, it can streamline sorting in nut processing facilities, assist supermarket cashiers in identifying nut types and pricing, and help consumers choose nuts that align with their dietary needs. In this paper, Using a public dataset of 2,850 images of Nuts, we trained a deep convolutional neural network to classify 5 types of nuts (Chestnut, Hazelnut, Nut Forest ,Nut Pecan ,Walnut). A deep learning technique that extensively applied to image recognition was used. We used 70% from image for training and 15% from image for validation 15% for testing. Our trained model achieved an accuracy of 100% on a held-out test set, demonstrating the feasibility of this approach.